Show HN: Soccer-Bench – Watch teams of LLM agents play 5v5 soccer

(darksinian.github.io)

9 points | by Darksinian 8 hours ago ago

1 comments

  • sixthcents27 15 minutes ago ago

    I'd be interested to see how a 2v2 with 1 strong model and 1 weaker model per team perform. I'm curious if the stronger model adapts to the weaker ones limitations or just tries to do everything itself instead.